Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34690
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events and statements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.21
    0.9%
    393
    +0.18
    0.8%
    362
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.21
    0.20
    393
    +0.18
    0.28
    159
    +0.15
    0.15
    Negative Logits
    ocument
    -0.86
    ancial
    -0.78
    perty
    -0.76
    redients
    -0.75
    needed
    -0.74
    inctions
    -0.72
    Frameworks
    -0.71
    heses
    -0.70
    Versions
    -0.69
    ãħĭãħĭ
    -0.69
    POSITIVE LOGITS
     standpoint
    1.55
     outset
    1.31
     vantage
    1.22
     perspective
    1.18
     infancy
    0.98
     viewpoint
    0.96
     inception
    0.94
     previous
    0.87
     playbook
    0.86
     sidelines
    0.85
    Activations Density 10.832%

    No Known Activations